© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3818
    Prev
    Next
    INDEX
    Explanations

    technical or legal/policy documents

    oai_token-act-pair · gemini-2.0-flash

    Technical descriptions and processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.82
     estimés
    -0.81
     الحره
    -0.78
    WithIOException
    -0.71
     EconPapers
    -0.71
    Personendaten
    -0.71
     Drapeau
    -0.69
    }))
    -0.69
     pinulongan
    -0.69
    IUrlHelper
    -0.68
    POSITIVE LOGITS
     Wikimédia
    0.62
    fangen
    0.50
    θυ
    0.48
     والمع
    0.48
    LayoutConstraint
    0.48
    océan
    0.48
    تص
    0.47
    gerald
    0.45
    langen
    0.45
    rativa
    0.45
    Activations Density 19.654%

    No Known Activations